Codex Knowledge Base
When Benchmarks Become Adversarial: METR's Sol Cheating Finding and What It Means for Coding Agent Trust
When Benchmarks Become Adversarial: METR’s Sol Cheating Finding and What It Means for Coding Agent Trust
Voice-Driven Development: How Codex CLI's Realtime V3 and ChatGPT Desktop Voice Reshape the Hands-Free Coding Loop
Voice-Driven Development: How Codex CLI’s Realtime V3 and ChatGPT Desktop Voice Reshape the Hands-Free Coding Loop
SkillCorpus and the 821K Skill Audit: What Crawling the Open Skill Ecosystem Reveals About Quality, Curation, and Your Codex CLI Skill Stack
SkillCorpus and the 821K Skill Audit: What Crawling the Open Skill Ecosystem Reveals About Quality, Curation, and Your Codex CLI Skill Stack
The Multi-Agent Auditability Gap: Why Encrypted Delegation Blinds Your Debugging — and What It Means for Enterprise Compliance
The Multi-Agent Auditability Gap: Why Encrypted Delegation Blinds Your Debugging — and What It Means for Enterprise Compliance
MOSAIC and the Command-Composition Kill Chain: How Individually Benign CLI Commands Combine Through Shared OS State to Breach Coding Agents — and Where Codex CLI's Sandbox Draws the Line
MOSAIC and the Command-Composition Kill Chain: How Individually Benign CLI Commands Combine Through Shared OS State to Breach Coding Agents — and Where Codex CLI’s Sandbox Draws the Line
The Meta-Harness Pattern: Orchestrating Codex CLI and Claude Code as Sub-Agents Through Pi
The Meta-Harness Pattern: Orchestrating Codex CLI and Claude Code as Sub-Agents Through Pi
The Ultra Mode Trade-Off: When GPT-5.6 Sol's Bigger Reasoning Budgets Backfire in Codex CLI
The Ultra Mode Trade-Off: When GPT-5.6 Sol’s Bigger Reasoning Budgets Backfire in Codex CLI
Model Routing Patterns for Coding Agents: A Sol, Terra, Luna Decision Framework
Model Routing Patterns for Coding Agents: A Sol, Terra, Luna Decision Framework
The Friendly Fire Exploit: How Defensive Code Review Becomes Remote Code Execution — and Why Codex CLI's Default Posture Blocks the Kill Chain
The Friendly Fire Exploit: How Defensive Code Review Becomes Remote Code Execution — and Why Codex CLI’s Default Posture Blocks the Kill Chain
Do Auto-Generated AGENTS.md Files Actually Help? What Three Studies Say About Instruction File Effectiveness
Do Auto-Generated AGENTS.md Files Actually Help? What Three Studies Say About Instruction File Effectiveness